知识卡片

普通读书笔记卡 · 8844.a · 生成模型:GPT-6

正则化平衡数据与解的偏好

理解等级:高级

本章求最小值||ℓs−Aℓw||²+λ||ℓw||²,以拟合观测和偏好较小范数的解取得折中。λ增大加强收缩,可能减弱噪声也增加偏差。小范数不等于直接要求空间平滑,具体重建效果取决于A和正则项。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      The regularization parameter, λ, determines the trade-off between explaining the observations and satisfying the regularization term. Figure 7.2: (a) Schematic drawing of a small-hole 1D pinhole camera, and (b) the visualization of its imaging matrices A, A–1, and the regularized inverse B. For the small-pinhole imager, all three matrices are identity matrices. (c) Large-hole 1D pinhole camera, and (d) the visualization of its imaging matrices.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第07章《作为线性系统的相机》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c007.xhtml) - 结论依据:摘录中关于正则化平衡数据与解的偏好的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:The regularization parameter, λ, determines the trade-off between explaining the observations and satisfying the regularization term. Figure 7.2: (a) Schematic drawing of a small-hole 1D pinhole camera, and (b) the visualization of its imaging matrices A, A–1, and the regularized inverse B. For the small-pinhole imager, all three matrices are identity matrices. (c) Large-hole 1D pinhole camera, and (d) the visualization of its imaging matrices.